Interpretable Graph Routing Network for Knowledge-based Visual Question Answering

Watch a research presentation from SIGIR 2024 that introduces an interpretable graph routing network designed for knowledge-based visual question answering. Explore how the authors Duokang Wang, Linmei Hu, Rui Hao, Yingxia Shao, Xin Lv, Liqiang Nie and Juanzi Li developed a step-by-step approach to improve visual question answering systems through graph-based knowledge routing. Learn about their methodology for enhancing interpretability in AI systems that combine visual and textual information processing during this 11-minute technical talk from the Question Answering and Summarisation session.